Parallelization of RSA Algorithm Based on Compute Unified Device Architecture

摘要：

In the domain of computer security, how to enhance the speed of RSA algorithm has been the research hot spot. With the recent tremendous increase in Graphics Processing Units computing capability as a co-processor of the CPU, Nvidia’s Compute Unified Device Architecture (CUDA) can greatly benefit single instruction multiple thread styled, computationally expensive programs. This paper presents a novel parallelized implement of RSA algorithm using JCUDA and Hadoop. Firstly the principle of tradition RSA algorithm is studied. Secondly, the parallel RSA algorithm is designed and realized in CUDA framework. Thirdly, with JCUDA, the RSA parallel algorithm implement function is called by each node in Hadoop cluster. Our experimental results demonstrate the speed of RSA algorithm enhanced dramatically compared to the original method on the CPU only.

关键词： GPU CUDA RSA JCUDA Hadoop

作者: Wenjun Fan Xudong Chen Xuefeng Li

作者单位: School of Software Engineering Beijing Jiaotong University Beijing, China IBM CDL Optim International Business Machines Corporation Beijing, China

会议类型: 国际会议

会议名称: The Ninth International Conference on Grid and Cloud Computing(第九届网格与云计算国际学术会议 GCC 2010)

会议地点: 南京

会议语种:英文

页码: 174-178

在线出版日期: 2010-11-01（万方平台首次上网日期，不代表论文的发表时间）